CN115236612A - Method and device for calibrating data of multi-millimeter wave radar - Google Patents
Method and device for calibrating data of multi-millimeter wave radar Download PDFInfo
- Publication number
- CN115236612A CN115236612A CN202111388584.0A CN202111388584A CN115236612A CN 115236612 A CN115236612 A CN 115236612A CN 202111388584 A CN202111388584 A CN 202111388584A CN 115236612 A CN115236612 A CN 115236612A
- Authority
- CN
- China
- Prior art keywords
- millimeter wave
- data
- radar
- laser radar
- affine matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/40—Means for monitoring or calibrating
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/865—Combination of radar systems with lidar systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The embodiment of the disclosure provides a method and a device for calibrating multi-millimeter wave radar data, wherein the method comprises the following steps: acquiring detection data of a laser radar and a plurality of millimeter wave radars, wherein the millimeter wave radars are installed at different angles of the same equipment; according to the obtained data, a point cloud matching method is utilized to obtain a first affine matrix between the laser radar and one of the millimeter wave radars and a second affine matrix between the laser radar and the other millimeter wave radar; obtaining a third affine matrix between one millimeter wave radar and the other millimeter wave radar according to the first affine matrix and the second affine matrix; and fusing the data detected by one millimeter wave radar to the data detected by the other millimeter wave radar according to the third affine matrix. According to the technical scheme, a plurality of millimeter wave radars installed at different angles are fused on the basis of data detected by the laser radars, and a more comprehensive detection visual field is constructed.
Description
Technical Field
The technical scheme disclosed by the invention relates to the technical field of automatic driving, in particular to a method and a device for calibrating multi-millimeter wave radar data.
Background
The environmental perception is a key part of an automatic driving system, is the front-end input of planning decisions, and provides an important basis for the planning decisions. Environmental awareness includes a number of tasks including traffic light detection, obstacle detection, lane line detection, etc., where obstacle detection is particularly important. The automatic driving vehicle needs to judge whether obstacles exist in the surrounding environment, so that planning decision is made, the running track of the automatic driving vehicle is determined, collision with other vehicles, pedestrians and the like is avoided, and safe automatic driving of the vehicle on a lane is realized.
In the related art, sensors such as a camera and a radar may be mounted on the autonomous vehicle to sense the surrounding environment through the sensors, and thus to control the driving of the autonomous vehicle according to the sensed environmental information. However, the detection visual field of the partial sensor is limited, for example, a single millimeter wave radar installed on the vehicle can only detect a local small-range visual field, which is not beneficial to the perception of the vehicle environment and affects the comprehensiveness and accuracy of the environmental perception.
Disclosure of Invention
The embodiment of the disclosure provides a method and a device for calibrating multi-millimeter wave radar data.
Specifically, the embodiment of the present disclosure is implemented by the following technical solutions:
according to a first aspect of the present disclosure, a method for calibrating multi-millimeter wave radar data is provided, where the method for calibrating multi-millimeter wave radar data includes:
respectively acquiring detection data of a laser radar and detection data of a plurality of millimeter wave radars, wherein the millimeter wave radars are installed at different angles of the same equipment, and the detection data of the laser radar and the detection data of any one of the millimeter wave radars are the detection data corresponding to the same object;
according to the obtained data, a point cloud matching method is utilized to obtain a first affine matrix between the laser radar and one of the millimeter wave radars and a second affine matrix between the laser radar and the other millimeter wave radar;
obtaining a third affine matrix between one millimeter wave radar and the other millimeter wave radar according to the first affine matrix and the second affine matrix;
and fusing the data detected by one millimeter wave radar to the data detected by the other millimeter wave radar according to the third affine matrix.
According to a second aspect of the present disclosure, a device for multi-millimeter wave radar data calibration is provided, the device for multi-millimeter wave radar data calibration including:
the data acquisition module is used for respectively acquiring detection data of a laser radar and detection data of a plurality of millimeter wave radars, wherein the millimeter wave radars are installed at different angles of the same equipment, and the detection data of the laser radar and the detection data of any one of the millimeter wave radars are the detection data corresponding to the same object;
the first calculation module is used for obtaining a first affine matrix between the laser radar and one of the millimeter wave radars and a second affine matrix between the laser radar and the other millimeter wave radar by using a point cloud matching method according to the obtained data;
the second calculation module is used for obtaining a third affine matrix between one millimeter wave radar and the other millimeter wave radar according to the first affine matrix and the second affine matrix;
and the data fusion module is used for fusing the data detected by one millimeter wave radar to the data detected by the other millimeter wave radar according to the third affine matrix.
According to a third aspect of the present disclosure, there is provided a computer readable storage medium storing machine readable instructions which, when invoked and executed by a processor, cause the processor to implement the method of multi-millimeter wave radar data targeting of any embodiment of the present disclosure.
According to a fourth aspect of the present disclosure, there is provided an electronic device, comprising a communication interface, a processor, a memory, and a bus, wherein the communication interface, the processor, and the memory are connected to each other via the bus; the memory stores machine readable instructions, and the processor executes the method for calibrating data of the multi-millimeter wave radar according to any one of the embodiments of the present disclosure by calling the machine readable instructions.
The method for calibrating the data of the multi-millimeter-wave radar provided by the embodiment of the disclosure is characterized in that the data detected by a plurality of millimeter-wave radars installed at different angles are calibrated and fused on the basis of the data detected by the laser radar, wherein the detection data of the laser radar and the detection data of any one of the millimeter-wave radars are the detection data corresponding to the same object.
The embodiments of the present disclosure are described in further detail below with reference to the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate one or more embodiments of the present disclosure or technical solutions in related arts, reference will be made to the following briefly introduced drawings which are used in the description of the embodiments or related arts, and obviously, the drawings in the following description are only some embodiments described in one or more embodiments of the present disclosure, and for those skilled in the art, other drawings can be obtained according to the drawings without inventive exercise:
fig. 1 is a flowchart of a method for calibrating data of a multi-millimeter wave radar provided according to an exemplary embodiment of the present disclosure;
FIG. 2 is a flow chart of yet another method for calibrating data for a multi-millimeter wave radar provided in accordance with an exemplary embodiment of the present disclosure;
fig. 3 is a block diagram of a multi-millimeter wave radar data calibration apparatus provided in accordance with an exemplary embodiment of the present disclosure.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure. The word "if," as used herein, may be interpreted as "at \8230; \8230when" or "when 8230; \823030when" or "in response to a determination," depending on the context.
The method of the embodiments of the present disclosure is explained in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method for calibrating data of a multi-millimeter wave radar according to an exemplary embodiment of the present disclosure, and as shown in fig. 1, the method according to the exemplary embodiment may include the following steps:
step S101, respectively obtaining detection data of a laser radar and a plurality of millimeter wave radars, wherein the millimeter wave radars are installed at different angles of the same equipment, and the detection data of the laser radar and any one of the millimeter wave radars are detection data corresponding to the same object.
In an alternative example, the detection field of view of the lidar may cover the sum of the detection fields of multiple millimeter wave radars mounted at different angles on the same device. I.e. objects that can be detected by any of the millimeter wave radars, the lidar may detect.
For example, the lidar may be a high beam lidar having a 360 degree field of view of detection. For another example, the lidar may be a high-beam lidar calibrated with a plurality of low-beam lidars and having a 360 degree field of view.
And S102, obtaining a first affine matrix between the laser radar and one of the millimeter wave radars and a second affine matrix between the laser radar and the other millimeter wave radar by using a point cloud matching method according to the obtained data.
In an optional example, a first affine matrix between the laser radar and one of the millimeter wave radars can be obtained by using a point cloud matching method according to the data detected by the laser radar and the data detected by the one of the millimeter wave radars. And according to the data detected by the laser radar and the data detected by the other millimeter wave radar, a second affine matrix between the laser radar and the other millimeter wave radar can be obtained by using a point cloud matching method.
And step S103, obtaining a third affine matrix between one millimeter wave radar and the other millimeter wave radar according to the first affine matrix and the second affine matrix.
In the present embodiment, the number of the "plurality of millimeter wave radars" may be 2 or more, and for example, may be 4 millimeter wave radars or 8 millimeter wave radars. In this embodiment, a manner of obtaining an affine matrix between any two millimeter wave radars is described, and the "any two millimeter wave radars" may be referred to as "one of the millimeter wave radars" and "the other millimeter wave radar", respectively.
In an optional example, the first affine matrix is an affine matrix between the laser radar and the one of the millimeter wave radars. The second affine matrix is an affine matrix between the laser radar and the another millimeter wave radar. According to the first affine matrix and the second affine matrix, through linear operation, an affine matrix between one of the millimeter wave radars and the other millimeter wave radar can be obtained, and the affine matrix can be called as a third affine matrix.
For example, one of the millimeter wave radars may be described as the millimeter wave radar J1, and the other may be described as the millimeter wave radar J2. The affine matrix between the laser radar and the millimeter wave radar J1 is A 1 The affine matrix between the laser radar and the millimeter wave radar J2 is A 2 Then A 2 -1 A 1 That is, the affine matrix between the millimeter wave radar J1 and the millimeter wave radar J2 may be referred to as a third affine matrix a 3 。
And step S104, fusing the data detected by one millimeter wave radar to the data detected by the other millimeter wave radar according to the third affine matrix.
In an optional example, the data detected by the one millimeter wave radar may be multiplied by the third affine matrix to obtain data having the same origin and positive direction as the other millimeter wave radar, so that the data detected by the one millimeter wave radar may be fused with the data detected by the other millimeter wave radar.
In an optional example, taking the number of the plurality of millimeter wave radars as 4 as an example, the above flow is further explained. Among them, 4 millimeter-wave radars may be written as a millimeter-wave radar J01, a millimeter-wave radar J02, a millimeter-wave radar J03, and a millimeter-wave radar J04.
Firstly, according to the obtained data, a point cloud matching method is utilized to obtain a first affine matrix A between the laser radar and the millimeter wave radar J01 01 A second affine matrix A between the laser radar and the millimeter wave radar J02 02 A third affine matrix A between the laser radar and the millimeter wave radar J03 03 A fourth affine matrix A between the laser radar and the millimeter wave radar J04 04 。
Then, according to the first affine matrix A 01 And a second affine matrix A 02 Calculating A 02 -1 A 01 And recording the result as A 12 I.e., an affine matrix between the millimeter wave radar J01 and the millimeter wave radar J02. The data detected by the millimeter wave radar J02 is pre-multiplied by the affine matrix A 12 That is, data having the same origin and positive direction as the data detected by the millimeter wave radar J01 can be obtained, so that the data detected by the millimeter wave radar J02 can be fused to the data detected by the millimeter wave radar J01.
According to the same method, the data detected by the millimeter wave radar J03 and the millimeter wave radar J04 may be sequentially fused to the data detected by the millimeter wave radar J01. Therefore, fusion of data detected by the four millimeter wave radars is realized.
In the method for calibrating data of the multi-millimeter wave radar in the embodiment, the data detected by the multiple millimeter wave radars are fused together on the basis of the data detected by the laser radar, so that a wider field of view is constructed.
Fig. 2 is a flowchart of yet another method for multi-millimeter wave radar data calibration according to an exemplary embodiment of the disclosure. In the present embodiment, the plurality of millimeter wave radars includes a first millimeter wave radar and a second millimeter wave radar. In the description of this embodiment, the same steps as those in any of the foregoing embodiments will be briefly described, and detailed descriptions thereof will be omitted, specifically referring to any of the foregoing embodiments. As shown in fig. 2, the method of this embodiment may include the following processes:
step S201, obtaining multi-frame point cloud data detected by a laser radar in a preset time period, and obtaining a moving track of an object detected by the laser radar according to the multi-frame point cloud data.
Wherein the lidar is mounted on an autonomous vehicle, and the autonomous vehicle is in an absolute stationary state during a time period in which probe data is acquired. The detection data of the laser radar is point cloud data which is a set comprising a series of points. In the preset time period, namely the time period for acquiring the detection data, the detection data of the laser radar are multi-frame point cloud data, and because the automatic driving vehicle is in an absolute static state at the moment, the laser radar is also in the absolute static state, so that no displacement change exists among the multi-frame point cloud data, and the multi-frame point cloud data are directly superposed to obtain the moving track of the object detected by the laser radar.
In an alternative example, the object detected by the lidar may be a driving automobile, a pedestrian on the road, a fence, or the like, which is not limited by the present disclosure.
Step S202, obtaining multi-frame data detected by a first millimeter wave radar and a second millimeter wave radar in the preset time period, calculating corresponding multi-frame point cloud data according to the multi-frame data, and obtaining moving tracks of objects detected by the first millimeter wave radar and the second millimeter wave radar according to the multi-frame point cloud data.
In an optional example, the first millimeter wave radar, the second millimeter wave radar, and the laser radar are mounted on the same autonomous vehicle, and the autonomous vehicle is in an absolute stationary state during a time period in which probe data is acquired.
In the preset time period, that is, the time period for acquiring the detection data, the first millimeter wave radar may detect multiple frames of data, where the data includes: distances, angles between a series of obstacles and the first millimeter wave radar, and moving speeds of the series of obstacles. And calculating the point cloud data of the series of obstacles relative to the first millimeter wave radar according to the distance and the angle, and further obtaining multi-frame point cloud data detected by the first millimeter wave radar, namely the detection data. At the moment, the automatic driving vehicle is in an absolute static state, so that the first millimeter wave radar is also in the absolute static state, displacement change among multiple frames of point cloud data does not exist, and the multiple frames of point cloud data can be directly superposed to obtain the moving track of the object detected by the first millimeter wave radar.
The acquisition mode of the moving track of the object detected by the second millimeter wave radar is the same as that of the moving track of the object detected by the first millimeter wave radar, and is not repeated.
In an alternative example, the objects detected by the first millimeter wave radar and the second millimeter wave radar may be running automobiles, pedestrians on roads, fences, and the like, wherein the objects detected by the first millimeter wave radar and the second millimeter wave radar may be different, but the objects detected by the first millimeter wave radar and the second millimeter wave radar may be detected by both of the laser radars.
Step S203, obtaining a first affine matrix between the laser radar and the first millimeter wave radar by a point cloud matching method according to the movement track of the object detected by the laser radar and the movement track of the object detected by the first millimeter wave radar. Wherein, the laser radar and the first millimeter wave radar detect the moving track of the same object.
The laser radar detects multi-frame 3D point cloud data, and corresponding multi-frame 2D point cloud data can be calculated according to the distance and the angle between a series of obstacles detected by the millimeter wave radar and the millimeter wave radar. Further, the multiple frames of 3D point clouds detected by the laser radar are overlapped, and then the moving track G1 of the object detected by the laser radar can be obtained. And superposing the multiframe 2D point cloud data detected by the millimeter wave radar to obtain the moving track G2 of the object detected by the millimeter wave radar. And obtaining an affine matrix between the laser radar and the millimeter wave radar by a point cloud matching method according to the moving track G1 and the moving track G2.
In an alternative example, the movement trajectories of the objects detected by the laser radar and the first millimeter wave radar may be linear movement trajectories, non-linear movement trajectories, or both linear and non-linear movement trajectories.
And S204, obtaining a second affine matrix between the laser radar and the second millimeter wave radar by a point cloud matching method according to the moving track of the object detected by the laser radar and the moving track of the object detected by the second millimeter wave radar.
Wherein, what the laser radar and the second millimeter wave radar detected is the moving track of the same object.
Step S205, obtaining a third affine matrix between the first millimeter wave radar and the second millimeter wave radar according to the first affine matrix and the second affine matrix.
And step S206, fusing the data detected by the first millimeter wave radar to the data detected by the second millimeter wave radar according to the third affine matrix.
In an optional example, the superimposed point cloud data detected by the first millimeter wave radar is multiplied by the third affine matrix to obtain point cloud data having the same origin and positive direction as the superimposed point cloud data detected by the second millimeter wave radar, so that the data detected by the first millimeter wave radar can be fused with the data detected by the second millimeter wave radar.
In an optional example, the processing process of the data fusion method may be performed by a cloud end connected to the autonomous vehicle, the laser radar and the millimeter wave radars installed in the autonomous vehicle upload detected data to the cloud end, and then the cloud end processes the data, and then the cloud end issues a related instruction to control a moving track of the autonomous vehicle, so that the autonomous vehicle avoids a series of obstacles and runs safely.
In an optional example, in order to further improve the efficiency of data processing, the processing process of the data fusion method may be performed by a processor installed on the autonomous vehicle, and the processor directly processes data detected by the laser radar and the millimeter wave radars installed on the autonomous vehicle and then sends an instruction, so that time is saved, the driving state of the autonomous vehicle is changed in time, and safety accidents are reduced.
According to the method for calibrating the data of the multi-millimeter-wave radar, the data detected by the plurality of millimeter-wave radars installed at different angles are fused on the basis of the data detected by the laser radar, so that a more comprehensive detection visual field is constructed, and a more reliable basis is provided for the driving of an automatic driving vehicle.
Corresponding to the embodiment of the multi-millimeter wave radar data calibration method, the disclosure also provides an embodiment of a multi-millimeter wave radar data calibration device.
Fig. 3 is a schematic structural diagram of a multi-millimeter wave radar data calibration apparatus in an exemplary embodiment of the disclosure, and as shown in fig. 3, the multi-millimeter wave radar data calibration apparatus may include:
the data acquisition module 11 is configured to acquire respective detection data of a laser radar and a plurality of millimeter wave radars, where the millimeter wave radars are installed at different angles of the same device, and the detection data of the laser radar and the millimeter wave radars are detection data corresponding to the same object;
the first calculation module 12 is configured to obtain, according to the obtained data, a first affine matrix between the laser radar and one of the millimeter wave radars and a second affine matrix between the laser radar and the other millimeter wave radar by using a point cloud matching method;
the second calculation module 13 is configured to obtain a third affine matrix between the one millimeter wave radar and the other millimeter wave radar according to the first affine matrix and the second affine matrix;
and the data fusion module 14 is configured to fuse the data detected by the one millimeter wave radar to the data detected by the other millimeter wave radar according to the third affine matrix.
Optionally, the detection field of the laser radar covers the sum of the detection fields of a plurality of millimeter wave radars installed in the same device at different angles.
Optionally, the data obtaining module 11 is configured to obtain respective detection data of a laser radar and a plurality of millimeter wave radars respectively, where the plurality of millimeter wave radars are installed at different angles of the same device, and when the detection data of the laser radar and any one of the millimeter wave radars is detection data corresponding to the same object, the data obtaining module includes:
acquiring multi-frame point cloud data detected by the laser radar in a preset time period, and obtaining a moving track of an object detected by the laser radar according to the multi-frame point cloud data;
for any millimeter wave radar, acquiring multi-frame data detected by the millimeter wave radar in the preset time period, calculating corresponding multi-frame point cloud data according to the multi-frame data, and obtaining a moving track of an object detected by the millimeter wave radar according to the multi-frame point cloud data;
the first calculating module 12, when configured to obtain, according to the obtained data, a first affine matrix between the laser radar and one of the millimeter wave radars by using a point cloud matching method, includes:
and obtaining a first affine matrix between the laser radar and one of the millimeter wave radars by a point cloud matching method according to the moving track of the object detected by the laser radar and the moving track of the object detected by the one of the millimeter wave radars.
Optionally, the movement track is a linear movement track and/or a non-linear movement track.
Optionally, the laser radar and the plurality of millimeter wave radars are mounted on the same autonomous vehicle, and the autonomous vehicle is in an absolute stationary state within a time period of acquiring the detection data.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiment, since it basically corresponds to the method embodiment, reference may be made to the partial description of the method embodiment for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the technical solution of the present disclosure. One of ordinary skill in the art can understand and implement it without inventive effort.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features specific to particular embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. In another aspect, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
The above description is only exemplary of the present disclosure and should not be taken as limiting the disclosure, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.
Claims (12)
1. A method for calibrating data of a multi-millimeter wave radar is characterized by comprising the following steps:
respectively acquiring respective detection data of a laser radar and a plurality of millimeter wave radars, wherein the millimeter wave radars are installed at different angles of the same equipment, and the detection data of the laser radar and any one of the millimeter wave radars are corresponding to the detection data of the same object;
according to the obtained data, a point cloud matching method is utilized to obtain a first affine matrix between the laser radar and one millimeter wave radar and a second affine matrix between the laser radar and the other millimeter wave radar;
obtaining a third affine matrix between one of the millimeter wave radars and the other millimeter wave radar according to the first affine matrix and the second affine matrix;
and fusing the data detected by one millimeter wave radar to the data detected by the other millimeter wave radar according to the third affine matrix.
2. The method according to claim 1, wherein the detection field of view of the lidar radar covers a sum of detection fields of a plurality of millimeter wave radars installed at different angles of the same device.
3. The method according to claim 1, wherein the separately acquiring detection data of each of a laser radar and a plurality of millimeter wave radars installed at different angles of a same device, the detection data of the laser radar and any one of the millimeter wave radars being detection data corresponding to a same object, comprises:
acquiring multi-frame point cloud data detected by the laser radar in a preset time period, and obtaining a moving track of an object detected by the laser radar according to the multi-frame point cloud data;
for any millimeter wave radar, acquiring multi-frame data detected by the millimeter wave radar in the preset time period, calculating corresponding multi-frame point cloud data according to the multi-frame data, and obtaining a moving track of an object detected by the millimeter wave radar according to the multi-frame point cloud data;
obtaining a first affine matrix between the laser radar and one of the millimeter wave radars by using a point cloud matching method according to the obtained data, wherein the first affine matrix comprises the following steps:
and obtaining a first affine matrix between the laser radar and one of the millimeter wave radars by a point cloud matching method according to the moving track of the object detected by the laser radar and the moving track of the object detected by the one of the millimeter wave radars.
4. The method according to claim 3, wherein the movement trajectory is a linear movement trajectory and/or a non-linear movement trajectory.
5. The method of claim 1 wherein the lidar and the plurality of millimeter wave radars are mounted on the same autonomous vehicle, and the autonomous vehicle is at an absolute standstill for a period of time during which the probe data is acquired.
6. An apparatus for multi-millimeter wave radar data calibration, the apparatus comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for respectively acquiring detection data of a laser radar and a plurality of millimeter wave radars, the millimeter wave radars are installed at different angles of the same equipment, and the detection data of the laser radar and any one of the millimeter wave radars are detection data corresponding to the same object;
the first calculation module is used for obtaining a first affine matrix between the laser radar and one of the millimeter wave radars and a second affine matrix between the laser radar and the other millimeter wave radar by using a point cloud matching method according to the obtained data;
the second calculation module is used for obtaining a third affine matrix between one millimeter wave radar and the other millimeter wave radar according to the first affine matrix and the second affine matrix;
and the data fusion module is used for fusing the data detected by one millimeter wave radar to the data detected by the other millimeter wave radar according to the third affine matrix.
7. The apparatus according to claim 6, wherein the detection field of view of the lidar covers a sum of detection fields of a plurality of millimeter wave radars installed at different angles of the same device.
8. The apparatus according to claim 6, wherein the data obtaining module, when configured to obtain respective detection data of a laser radar and a plurality of millimeter wave radars respectively, wherein the plurality of millimeter wave radars are installed at different angles of a same device, and the detection data of the laser radar and any one of the millimeter wave radars is detection data corresponding to a same object, includes:
acquiring multi-frame point cloud data detected by the laser radar in a preset time period, and obtaining a moving track of an object detected by the laser radar according to the multi-frame point cloud data;
for any millimeter wave radar, obtaining multi-frame data detected by the millimeter wave radar in the preset time period, calculating corresponding multi-frame point cloud data according to the multi-frame data, and obtaining a moving track of an object detected by the millimeter wave radar according to the multi-frame point cloud data;
the first calculation module, when being configured to obtain, according to the obtained data, a first affine matrix between the laser radar and one of the millimeter wave radars by using a point cloud matching method, includes:
and obtaining a first affine matrix between the laser radar and one of the millimeter wave radars by a point cloud matching method according to the moving track of the object detected by the laser radar and the moving track of the object detected by the one of the millimeter wave radars.
9. The apparatus of claim 8, wherein the movement track is a linear movement track and/or a non-linear movement track.
10. The apparatus of claim 6, wherein the lidar and the plurality of millimeter wave radars are mounted on the same autonomous vehicle, and the autonomous vehicle is in an absolute stationary state during the time period in which the probe data is acquired.
11. A computer readable storage medium having stored thereon machine readable instructions which, when invoked and executed by a processor, cause the processor to carry out the method of any of claims 1 to 5.
12. An electronic device is characterized by comprising a communication interface, a processor, a memory and a bus, wherein the communication interface, the processor and the memory are connected with each other through the bus; the memory has stored therein machine-readable instructions, the processor executing the method of any one of claims 1 to 5 by calling the machine-readable instructions.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111388584.0A CN115236612A (en) | 2021-11-22 | 2021-11-22 | Method and device for calibrating data of multi-millimeter wave radar |
| PCT/CN2022/071112 WO2023087522A1 (en) | 2021-11-22 | 2022-01-10 | Data calibration method and apparatus for multiple millimeter-wave radars |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111388584.0A CN115236612A (en) | 2021-11-22 | 2021-11-22 | Method and device for calibrating data of multi-millimeter wave radar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115236612A true CN115236612A (en) | 2022-10-25 |
Family
ID=83666110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111388584.0A Pending CN115236612A (en) | 2021-11-22 | 2021-11-22 | Method and device for calibrating data of multi-millimeter wave radar |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115236612A (en) |
| WO (1) | WO2023087522A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116819469B (en) * | 2023-08-28 | 2023-11-10 | 南京慧尔视智能科技有限公司 | Multi-radar target position synchronization method, device, equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101932041B1 (en) * | 2017-03-02 | 2018-12-24 | 충북대학교 산학협력단 | Method and apparatus for calibration of dual Lidar sensors |
| CN109975773B (en) * | 2018-12-28 | 2023-09-29 | 文远知行有限公司 | Millimeter wave radar calibration method, device, equipment and storage medium |
| CN109581338B (en) * | 2019-01-14 | 2021-01-08 | 中国科学院计算技术研究所 | System and method for calibrating external parameters of multiple laser radars |
| CN110579764B (en) * | 2019-08-08 | 2021-03-09 | 北京三快在线科技有限公司 | Registration method and device for depth camera and millimeter wave radar, and electronic equipment |
| CN112684432B (en) * | 2019-10-18 | 2024-04-16 | 武汉万集光电技术有限公司 | Laser radar calibration method, device, equipment and storage medium |
| CN111077506B (en) * | 2019-12-12 | 2022-04-19 | 苏州智加科技有限公司 | Method, device and system for calibrating millimeter wave radar |
-
2021
- 2021-11-22 CN CN202111388584.0A patent/CN115236612A/en active Pending
-
2022
- 2022-01-10 WO PCT/CN2022/071112 patent/WO2023087522A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023087522A1 (en) | 2023-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3032221B1 (en) | Method and system for improving accuracy of digital map data utilized by a vehicle | |
| EP3644294B1 (en) | Vehicle information storage method, vehicle travel control method, and vehicle information storage device | |
| US10604156B2 (en) | System and method for adjusting a road boundary | |
| US10121367B2 (en) | Vehicle lane map estimation | |
| JP6714513B2 (en) | An in-vehicle device that informs the navigation module of the vehicle of the presence of an object | |
| CN105109484B (en) | Target disorders object determines method and device | |
| US20200226932A1 (en) | Vehicle dispatch system, autonomous driving vehicle, and vehicle dispatch method | |
| US20120310516A1 (en) | System and method for sensor based environmental model construction | |
| Rawashdeh et al. | Collaborative automated driving: A machine learning-based method to enhance the accuracy of shared information | |
| US20180050694A1 (en) | Method and device for monitoring a setpoint trajectory to be traveled by a vehicle for being collision free | |
| US20210107487A1 (en) | Apparatus for controlling lane change of autonomous vehicle and method thereof | |
| CN110632617B (en) | Laser radar point cloud data processing method and device | |
| CN112418092B (en) | Fusion method, device, equipment and storage medium for obstacle perception | |
| CN111508276B (en) | High-precision map-based V2X reverse overtaking early warning method, system and medium | |
| US11640172B2 (en) | Vehicle controls based on reliability values calculated from infrastructure information | |
| CN112394725A (en) | Predictive and reactive view-based planning for autonomous driving | |
| CN114518574A (en) | Kurtosis-based pruning for sensor fusion systems | |
| CN114385692A (en) | Vehicle driving data processing method and system, storage medium and electronic equipment | |
| CN112230211A (en) | Vehicle positioning method and device, storage medium and vehicle | |
| CN112241167A (en) | Information processing method and device in automatic driving and storage medium | |
| CN115236612A (en) | Method and device for calibrating data of multi-millimeter wave radar | |
| CN117387647A (en) | Road planning method integrating vehicle-mounted sensor data and road sensor data | |
| US20230168368A1 (en) | Guardrail estimation method based on multi-sensor data fusion, and vehicle-mounted device | |
| Polychronopoulos et al. | Extended path prediction using camera and map data for lane keeping support | |
| US20210403056A1 (en) | Convolution operator selection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |